Deep learning for survival prediction in triple-negative breast cancer: development and validation in real-world cohorts

Abstract Triple-negative breast cancer (TNBC) is an aggressive and heterogeneous disease, highlighting the need for better patient stratification to guide treatment. We developed a deep learning-based survival model and an individualized prognosis system using data from 37,818 TNBC patients in the S...

Full description

Saved in:
Bibliographic Details
Main Authors: Yiyue Xu, Butuo Li, Bing Zou, Bingjie Fan, Shijiang Wang, Jinming Yu, Taotao Dong, Linlin Wang
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-16331-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226485779398656
author Yiyue Xu
Butuo Li
Bing Zou
Bingjie Fan
Shijiang Wang
Jinming Yu
Taotao Dong
Linlin Wang
author_facet Yiyue Xu
Butuo Li
Bing Zou
Bingjie Fan
Shijiang Wang
Jinming Yu
Taotao Dong
Linlin Wang
author_sort Yiyue Xu
collection DOAJ
description Abstract Triple-negative breast cancer (TNBC) is an aggressive and heterogeneous disease, highlighting the need for better patient stratification to guide treatment. We developed a deep learning-based survival model and an individualized prognosis system using data from 37,818 TNBC patients in the SEER database (split into training [65%], validation [17.5%], and test [17.5%] sets). The survival model, built using the pysurvival algorithm, achieved strong performance (C-index: 0.824 in validation set, 0.816 in test set), outperforming traditional methods (CPH: 0.781 and 0.785; RSH: 0.779 and 0.766). External validation on a real-world cohort confirmed its robustness (C-index: 0.758). Our individualized prognosis system also showed higher predictive accuracy than traditional AJCC-TNM staging (AUC 0.821 vs. 0.771). These tools improve TNBC prognosis assessment, enable better patient stratification, and provide clinicians with significant treatment recommendations.
format Article
id doaj-art-3212d009c90c44059e8b00f0495e2bc2
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-3212d009c90c44059e8b00f0495e2bc22025-08-24T11:17:21ZengNature PortfolioScientific Reports2045-23222025-08-0115111310.1038/s41598-025-16331-8Deep learning for survival prediction in triple-negative breast cancer: development and validation in real-world cohortsYiyue Xu0Butuo Li1Bing Zou2Bingjie Fan3Shijiang Wang4Jinming Yu5Taotao Dong6Linlin Wang7Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical SciencesDepartment of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical SciencesDepartment of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical SciencesDepartment of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical SciencesDepartment of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical SciencesDepartment of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical SciencesDepartment of Obstetrics and Gynecology, Qilu Hospital of Shandong UniversityDepartment of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical SciencesAbstract Triple-negative breast cancer (TNBC) is an aggressive and heterogeneous disease, highlighting the need for better patient stratification to guide treatment. We developed a deep learning-based survival model and an individualized prognosis system using data from 37,818 TNBC patients in the SEER database (split into training [65%], validation [17.5%], and test [17.5%] sets). The survival model, built using the pysurvival algorithm, achieved strong performance (C-index: 0.824 in validation set, 0.816 in test set), outperforming traditional methods (CPH: 0.781 and 0.785; RSH: 0.779 and 0.766). External validation on a real-world cohort confirmed its robustness (C-index: 0.758). Our individualized prognosis system also showed higher predictive accuracy than traditional AJCC-TNM staging (AUC 0.821 vs. 0.771). These tools improve TNBC prognosis assessment, enable better patient stratification, and provide clinicians with significant treatment recommendations.https://doi.org/10.1038/s41598-025-16331-8Triple-negative breast cancerDeep learningPrognosis modelSurvival prediction system
spellingShingle Yiyue Xu
Butuo Li
Bing Zou
Bingjie Fan
Shijiang Wang
Jinming Yu
Taotao Dong
Linlin Wang
Deep learning for survival prediction in triple-negative breast cancer: development and validation in real-world cohorts
Scientific Reports
Triple-negative breast cancer
Deep learning
Prognosis model
Survival prediction system
title Deep learning for survival prediction in triple-negative breast cancer: development and validation in real-world cohorts
title_full Deep learning for survival prediction in triple-negative breast cancer: development and validation in real-world cohorts
title_fullStr Deep learning for survival prediction in triple-negative breast cancer: development and validation in real-world cohorts
title_full_unstemmed Deep learning for survival prediction in triple-negative breast cancer: development and validation in real-world cohorts
title_short Deep learning for survival prediction in triple-negative breast cancer: development and validation in real-world cohorts
title_sort deep learning for survival prediction in triple negative breast cancer development and validation in real world cohorts
topic Triple-negative breast cancer
Deep learning
Prognosis model
Survival prediction system
url https://doi.org/10.1038/s41598-025-16331-8
work_keys_str_mv AT yiyuexu deeplearningforsurvivalpredictionintriplenegativebreastcancerdevelopmentandvalidationinrealworldcohorts
AT butuoli deeplearningforsurvivalpredictionintriplenegativebreastcancerdevelopmentandvalidationinrealworldcohorts
AT bingzou deeplearningforsurvivalpredictionintriplenegativebreastcancerdevelopmentandvalidationinrealworldcohorts
AT bingjiefan deeplearningforsurvivalpredictionintriplenegativebreastcancerdevelopmentandvalidationinrealworldcohorts
AT shijiangwang deeplearningforsurvivalpredictionintriplenegativebreastcancerdevelopmentandvalidationinrealworldcohorts
AT jinmingyu deeplearningforsurvivalpredictionintriplenegativebreastcancerdevelopmentandvalidationinrealworldcohorts
AT taotaodong deeplearningforsurvivalpredictionintriplenegativebreastcancerdevelopmentandvalidationinrealworldcohorts
AT linlinwang deeplearningforsurvivalpredictionintriplenegativebreastcancerdevelopmentandvalidationinrealworldcohorts